skills.rest
surfingalien
surfingalienCOMMUNITY
Explore all skills by this author →
GitHub

wiki-query

Query indexed wiki pages using SQLite FTS5 BM25 full-text search with citations.

1|Updated May 6, 2026
Search Tags:#retrieval#citations#sqlite#full-text search#wiki#bm25#fts5
One-click install
npx skills add https://github.com/surfingalien/FinSurfing --skill wiki-query-surfingalien
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wiki-query
Source: https://github.com/surfingalien/FinSurfing/tree/main/.claude/skills/wiki-query
Command: npx skills add https://github.com/surfingalien/FinSurfing --skill wiki-query-surfingalien

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? It prevents duplicated research and lost knowledge by letting you search existing wiki pages before writing new content or answering domain questions, returning ranked passages with verifiable citations. ## Core Features & Use Cases - BM25 Full-Text Search: Search across all wikis or a single wiki slug with ranked results, snippets, and JSON output. - Related Page Discovery: Find adjacent pages by reusing a page's title and summary as the search seed. - Citation Enforcement: Every hit is cited as [wiki:<slug>] <title> — <rel_path> so claims stay traceable. - Use Case: Before drafting a new wiki page on episodic memory, run a search to confirm whether the topic is already covered, then cite the existing pages instead of duplicating them. ## Quick Start Ask the wiki what it says about episodic memory by running the search command with your query and reviewing the top ranked passages.

Frequently Asked Questions about wiki-query

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search wiki pages with full-text search?▼

Run query.js search with your query string to perform SQLite FTS5 BM25 full-text search across all indexed wikis. Add --wiki to restrict to one slug, --limit to control result count, and --json for machine-readable output.

What is BM25 ranking in SQLite FTS5?▼

BM25 is the default relevance ranking function in SQLite FTS5, scoring documents by term frequency and document length normalization. In this tool, lower (more negative) rank values indicate better matches.

How do I find related pages in a wiki?▼

Use query.js related with a wiki slug and page path. It reuses the page's title and summary as the search query, then returns the top matching pages excluding the page itself.

Why does wiki-query fail with a missing store error?▼

The script requires the compiled store at dist/db/store.js in the pro-workflow project. Run npm install and npm run build in that project root before executing any query commands.

Does wiki-query support semantic or vector search?▼

No, the current version supports BM25 keyword ranking only. Vector search via sqlite-vec is planned for a later release, along with MMR re-ranking for result diversity.

Related Skills

Explore More Education & Research Skills→
AradotsoAradotso
4

fieldtheory-cli

Sync X/Twitter bookmarks locally and index them with SQLite FTS5.

Official
Advanced
surebelisurebeli

wiki-lint

Detect broken links, orphan pages, and schema violations in wiki repositories.

Community
Intermediate
Mercurium-AnalyticsMercurium-Analytics

hybrid-lexical-semantic

Fuse BM25 lexical relevance with vector semantic similarity in pgsv.hybrid_search.

Official
Advanced
BEKO2210BEKO2210
15

search

Search knowledge bases semantically with vector embeddings and keyword fallback.

Community
Advanced